modelscope / KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech
☆507Updated last year
Alternatives and similar repositories for KAN-TTS:
Users that are interested in KAN-TTS are comparing it to the libraries listed below
- 基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏☆261Updated last year
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆387Updated 10 months ago
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,184Updated last year
- 使用vllm加速cosyvoice2的推理☆232Updated last week
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆261Updated 3 weeks ago
- 📣 商用级开源语音自动识别程序库，开箱即用，全平台支持，中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide …☆545Updated 11 months ago
- Text Normalization & Inverse Text Normalization☆569Updated 5 months ago
- A 10000+ hours dataset for Chinese speech recognition☆528Updated last year
- Unoffical implementation of Megatts2☆283Updated last year
- 这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小…☆510Updated 2 years ago
- Pseudo Streaming SenseVoice with Hotwords☆245Updated last month
- ☆195Updated 7 months ago
- ☆684Updated 10 months ago
- Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei …☆473Updated 2 years ago
- 基于PyTorch的VITS-BigVGAN的tts中文模型，加入韵律预测模型。☆194Updated 2 years ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆486Updated 3 weeks ago
- chinese speech pretrained models☆1,106Updated 8 months ago
- VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design☆553Updated last year
- 本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型，同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法☆266Updated last week
- ☆358Updated 9 months ago
- unofficial vits2-TTS implementation in pytorch☆517Updated last year
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆539Updated 2 months ago
- The dataset of Speech Recognition☆413Updated 3 months ago
- 第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。☆554Updated last year
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆396Updated last year
- text to speech using autoregressive transformer and VITS☆238Updated last year
- ☆112Updated last year
- SubFix: Efficient Web-Based Audio Subtitle Editing and Multilingual Automatic Annotation Tool.☆203Updated last year
- FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion☆662Updated 3 months ago
- [ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching☆973Updated 3 weeks ago